Hy3 295B A21B PrismaQuant 2.8bit gguf vllm needs about 116.6 GB of memory at its main file (a 103.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
Hy3 295B A21B PrismaQuant 2.8bit gguf vllm is a 295B-parameter model in GGUF format, quantized by rdtand. The repository has 1 quant file, from 103.7 GB to 103.7 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 103.7 GB (3 parts) | 116.6 GB | Too big | Get file → |
What GPU do you need for Hy3 295B A21B PrismaQuant 2.8bit gguf vllm?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hy3 295B A21B PrismaQuant 2.8bit gguf vllm
How much VRAM does Hy3 295B A21B PrismaQuant 2.8bit gguf vllm need?
About 116.6 GB at its main file with an 8K context window. That is the 103.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Hy3 295B A21B PrismaQuant 2.8bit gguf vllm on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 116.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Hy3 295B A21B PrismaQuant 2.8bit gguf vllm GGUF?
It depends on the quant: file is 103.7 GB.
Where can I download Hy3 295B A21B PrismaQuant 2.8bit gguf vllm GGUF?
The files are on Hugging Face in the rdtand/Hy3-295B-A21B-PrismaQuant-2.8bit-gguf-vllm repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Hy3 295B A21B PrismaQuant 2.8bit gguf vllm use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.